Smart Homes (SHs), as subsets of the Internet of Things (IoT), make use of Machine Learning and Arti cial Intelligence tools to provide technology-enabled solutions which assist their occupants and users with their Activities of Daily Living (ADL). Some SH provide always-present, health management support and care services. Having these services provided at home enables SH occupants such as the elderly and disabled to continue to live in their own homes and localities thus aiding Ageing In Place goals and eliminating the need for them to be relocated in order to be able to continue receiving the same support and services. Introducing and interconnecting smart, autonomous systems in homes to enable these service provisions and Assistance Technologies (AT) requires that certain interfaces in, and connections to, SH are exposed to the Internet, among other public-facing networks. This introduces the potential for cyber-physical attacks to be perpetrated through, from and against SH. Apart from the actual threats posed by these attacks to SH occupants and their homes, the potential that these attacks might occur can adversely a ect the adoption or uptake of SH solutions. This thesis identi es key attributes of the di erent elements (things or nodes and rooms or zones) in SHs and the relationships that exist between these elements. These relationships can be used to build SH security baselines for SHs such that any deviations from this baseline is described as anomalous. The thesis demonstrates the application of these relationships to Anomaly Detection (AD) through the analysis of several hypothetical scenarios and the decisions reached about whether they are normal or anomalous. This thesis also proposes an Internet of Things Digital Forensics Framework (IDFF), a Forensics Edge Management System (FEMS), a FEMS Decision-Making Algorithm (FDMA) and an IoT Incident Response plan. These tools can be combined to provide proactive (autonomous and human-led) Digital Forensics services within cyber-physical environments like the Smart Home.
Identifer | oai:union.ndltd.org:bl.uk/oai:ethos.bl.uk:738064 |
Date | January 2015 |
Creators | Oriwoh, Edewede |
Publisher | University of Bedfordshire |
Source Sets | Ethos UK |
Detected Language | English |
Type | Electronic Thesis or Dissertation |
Source | http://hdl.handle.net/10547/622486 |
Page generated in 0.0038 seconds